© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151081
    Prev
    Next
    INDEX
    Explanations

    fruit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arend
    -0.29
    -fin
    -0.27
    nger
    -0.25
    tré
    -0.25
    æĬ±
    -0.24
     rum
    -0.24
    æĤ«
    -0.24
     Hep
    -0.24
    两端
    -0.24
    Ho
    -0.24
    POSITIVE LOGITS
     chast
    0.26
    丢失
    0.25
    pare
    0.24
    æįĮ
    0.24
    éĢĿ
    0.24
    大ä¼ļä¸Ĭ
    0.24
     stoi
    0.24
    onor
    0.23
     packing
    0.23
    ause
    0.23
    Activations Density 0.132%

    No Known Activations